INDEX

Explanations

phrases related to consent and support

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hed

-0.15

odash

-0.15

aucoup

-0.15

zcze

-0.14

obia

-0.14

hed

-0.14

 Functor

-0.14

yne

-0.14

eneric

-0.14

illion

-0.14

POSITIVE LOGITS

zt

0.16

anken

0.15

sey

0.15

Äĥm

0.15

aru

0.14

 input

0.14

èĪį

0.14

 seal

0.14

 Seal

0.14

Activations Density 0.244%

phrases related to consent and support

No Comments

No Known Activations